Publication: Comparative Analysis on Blood Cell Image Segmentation
No Thumbnail Available
Date
2013
Journal Title
Journal ISSN
Volume Title
Publisher
Atlantis Press
Abstract
Image segmentation is an important phase in image recognition system. In medical imaging such as blood cell analysis, it becomes a crucial step in quantitative cytophotometry. Currently, blood cell images become predominantly valuable in medical diagnostics tools. In this paper, we present a comparative analysis on several segmentation algorithms. Three selected common approaches, that are Fuzzy c-means, K-means and Mean-shift were presented. Blood cell images that are infected with malaria parasites at various stages were tested. The most suitable method that is K-means was selected. K-means has been enhanced by integrating Median-cut algorithm to further improve the segmentation process. The proposed integrated method has shown a significant improvement in the number of selected regions.
Description
Keywords
Segmentation, Blood Cell Images, Means-shift, Fuzzy c-means, K-means, Median-cut